© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 4471
    Prev
    Next
    INDEX
    Explanations

    concepts related to formal methods and parameters in theoretical frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    reasoning or methods

    np_acts-logits-general · gemini-2.0-flash

    importance and necessity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Affirmed
    -0.56
     synced
    -0.55
     perfekte
    -0.51
     professionally
    -0.51
    engertian
    -0.49
     Personal
    -0.49
    strconv
    -0.48
     synchronous
    -0.48
    MessageWindow
    -0.48
     linkovi
    -0.47
    POSITIVE LOGITS
     Walkover
    0.76
     سكانية
    0.70
    abestanden
    0.67
     Exploit
    0.63
     بيها
    0.63
    省市镇
    0.62
     betweenstory
    0.60
     apellidos
    0.59
    oopy
    0.58
    Источники
    0.57
    Activations Density 2.370%

    No Known Activations